You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Since I needed a different version of normalization I've copied, modified and renamed ndarray-normalize to ndarray-sample-normalize. This performs the normalization with the sample statistics, i.e. the n-1 calculation for the standard deviation.
Since I needed a different version of normalization I've copied, modified and renamed ndarray-normalize to ndarray-sample-normalize. This performs the normalization with the sample statistics, i.e. the n-1 calculation for the standard deviation.
See Wikipedia Standard Deviation. See also the matlab zscore function which has a flag 0 - for sample standard deviation and 1 - for population standard deviation.
The repository is at https://github.com/bldrvnlw/ndarray-sample-normalize including an operational test. Would people be intrested in having this in scijs?
An alternative might be to add a flag to the original ndarray-normalize instead.
The text was updated successfully, but these errors were encountered: